Invariant discriminative regions for image matching under viewpoint and illumination changes

被引：0

作者：

Shao, Ling ^{[1
]}

Bao, Lei ^{[1
]}

Kirenko, Ihor ^{[1
]}

机构：

[1] Philips Res Labs, Eindhoven, Netherlands

来源：

PROCEEDINGS OF THE EIGHTH IASTED INTERNATIONAL CONFERENCE ON SIGNAL AND IMAGE PROCESSING | 2006年

关键词：

invariant regions; image matching; orientation histogram; repeatability;

D O I：

暂无

中图分类号：

TP31 [计算机软件];

学科分类号：

081202 ; 0835 ;

摘要：

A viewpoint and illumination invariant region detector is presented for image matching purposes. The regions are detected based on the local structure and information content. The stability of the algorithm is demonstrated by the high repeatability rate of the detected regions. Image matching experiments are carried out using generalized color moment invariants as the invariant descriptor. The experimental results show the good performance of our detector for image matching and the further applicability for vision applications.

引用

页码：105 / 108

页数：4

共 9 条

[1] Direct computation of shape cues using scale-adapted spatial derivative operators [J].